| 1 |
Enhancing multimodal analogical reasoning with Logic Augmented Generation |
提出逻辑增强生成框架，提升多模态类比推理在隐式知识提取中的性能 |
large language model multimodal |
|
|
| 2 |
HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation |
提出HypoBench：一个系统且规范的假设生成基准评测框架 |
large language model |
|
|
| 3 |
Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs |
提出NPPC：一个可无限扩展的推理基准，用于评估大型语言模型在NP问题上的能力。 |
large language model |
|
|
| 4 |
ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search |
ARise：通过风险自适应搜索增强知识推理，解决开放域复杂推理难题。 |
large language model |
✅ |
|
| 5 |
Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment |
探索人格化LLM在道德机器实验中的对齐问题 |
large language model |
|
|